Ready to supercharge your AI agents?

Install any skill in seconds. Free to start, no credit card required.

Nimble Web Search · leoyeai | DecimalAI

Researchby leoyeai

Nimble Web Search

Real-time web intelligence powered by Nimble Search API. Perform intelligent web searches with 8 specialized focus modes (general, coding, news, academic, shopping, social, geo, location). This skill provides real-time search results when you need to search the web, find current information, discover URLs, research topics, or gather up-to-date data.

SkillScore

SkillScore95/100

Test results 95

Safety

3/3 safety checks passed

Code scan
Intent
Content

What it changes

27%95%of test cases passed +68 pts

Without skill6 of 22

With skill21 of 22

16 fixed5 passed either way0 still failing1 broke

Measured on gemini-3.6-flash8/8/2026v121 comparable

Track record

Agent runs: 0; All time

See one task, with and without the skill

One test taskI need to quickly generate a list of 10 relevant article URLs comparing PostgreSQL vs MySQL for a blog post outline. Output the JSON payload for `./scripts/search.sh`.

Without the skillMissed

With the skillPassed

Same model, same task. Answers are capped and redacted.

Use this skill

Your agent runs on

Adds every file the skill has, pinned so you can update it. No account needed.

pip install "decimalai>=0.15"
decimalai skills add leoyeai-nimble-web-search
claude --plugin-dir "$(git rev-parse --show-toplevel 2>/dev/null || pwd)/.agents"

The same install from Python, for a notebook or a setup script.

Install

pip install "decimalai>=0.15"

Add the skill

from decimalai import skillpkg

# Writes .agents/skills and .decimal/skills.toml. Safe to run twice.
result = skillpkg.add("leoyeai-nimble-web-search")
if result.exit_code:
    raise SystemExit(result.problems)

print("Added. Start Claude Code with the command below.")

Start Claude Code with it

claude --plugin-dir "$(git rev-parse --show-toplevel 2>/dev/null || pwd)/.agents"

Type these in a Claude Code session. No account or API key. It writes the skill and any files it bundles, and asks first when its safety rating isn't Passed.

Add the DecimalAI plugin, once

/plugin marketplace add decimal-labs/decimalai-claude-plugins
/plugin install decimalai@decimalai

Install this skill

/decimalai:install leoyeai-nimble-web-search

The plugin needs python3 and curl on your machine.

No Python or account. Claude Code picks it up in its next session.

Save it into your project

curl -fsSL --create-dirs -o .claude/skills/leoyeai-nimble-web-search/SKILL.md https://app.decimal.ai/s/leoyeai-nimble-web-search/SKILL.md

Copy SKILL.md

Save it in your project, as

.claude/skills/leoyeai-nimble-web-search/SKILL.md

This gets SKILL.md only. The skill's 5 other files are not included.

Other ways to add it

Claude Code docs

agent_config() hands your agent the skill. With no DecimalAI key it reads your project's files and sends nothing. Needs SDK 0.27 or newer.

Install

pip install "decimalai[claude-agent-sdk]"
decimalai skills add leoyeai-nimble-web-search

Add it to your agent

import asyncio

from claude_agent_sdk import ClaudeAgentOptions
from decimalai.claude_agent_sdk import agent_config

# With no DECIMAL_API_KEY this reads the skills your project lists, from disk.
support = agent_config("support", fallback="You are a helpful agent.")

async def main():
    question = "Hello!"
    async with support.run(question) as run:  # one user message, one run
        async for message in run.query(options=ClaudeAgentOptions(max_turns=6)):
            print(message)

# In a notebook or async code: await main()
asyncio.run(main())

Prefer its own loader? ClaudeAgentOptions(plugins=[skills_plugin()], skills="all") reads the same folder. Use one or the other: a skill delivered both ways reaches the prompt twice.

The same install from Python, for a notebook or a setup script. agent_config() hands your agent the skill. With no DecimalAI key it reads your project's files and sends nothing. Needs SDK 0.27 or newer.

Install

pip install "decimalai[claude-agent-sdk]"

Add it to your agent

from decimalai import skillpkg

# Writes .agents/skills and .decimal/skills.toml. Safe to run twice.
result = skillpkg.add("leoyeai-nimble-web-search")
if result.exit_code:
    raise SystemExit(result.problems)

import asyncio

from claude_agent_sdk import ClaudeAgentOptions
from decimalai.claude_agent_sdk import agent_config

# With no DECIMAL_API_KEY this reads the skills your project lists, from disk.
support = agent_config("support", fallback="You are a helpful agent.")

async def main():
    question = "Hello!"
    async with support.run(question) as run:  # one user message, one run
        async for message in run.query(options=ClaudeAgentOptions(max_turns=6)):
            print(message)

# In a notebook or async code: await main()
asyncio.run(main())

Prefer its own loader? ClaudeAgentOptions(plugins=[skills_plugin()], skills="all") reads the same folder. Use one or the other: a skill delivered both ways reaches the prompt twice.

No DecimalAI package. The whole skill goes in every prompt, and nothing pins or updates it.

Copy SKILL.md

Save it in your project, as

.agents/skills/leoyeai-nimble-web-search/SKILL.md

Give it to your agent

import asyncio
from pathlib import Path
from claude_agent_sdk import ClaudeAgentOptions, query

skill = Path(".agents/skills/leoyeai-nimble-web-search/SKILL.md").read_text()
options = ClaudeAgentOptions(system_prompt=f"You are a helpful agent.\n\n{skill}", max_turns=6)

async def main():
    async for message in query(prompt="Hello!", options=options):
        print(message)

# In a notebook or async code: await main()
asyncio.run(main())

This gets SKILL.md only. The skill's 5 other files are not included.

Other ways to add it

Claude Agent SDK docs

agent_config() hands your agent the skill. With no DecimalAI key it reads your project's files and sends nothing. Needs SDK 0.27 or newer.

Install

pip install "decimalai[openai-agents]"
decimalai skills add leoyeai-nimble-web-search

Add it to your agent

from agents import Agent, Runner
from decimalai.openai_agents import agent_config

# With no DECIMAL_API_KEY this reads the skills your project lists, from disk.
support = agent_config("support", fallback="You are a helpful agent.")

agent = Agent(
    name=support.name,
    instructions=support.instructions,  # your prompt, then the skill list
    tools=[*support.tools],             # your tools, then load_skill
)
# In a notebook or async code: result = await Runner.run(agent, "Hello!")
result = Runner.run_sync(agent, "Hello!")

Using SandboxAgent? capabilities=[Shell(), decimalai.openai_agents.sandbox_skills()] points its own loader at the same folder.

Install

pip install "decimalai[openai-agents]"

Add it to your agent

from decimalai import skillpkg

# Writes .agents/skills and .decimal/skills.toml. Safe to run twice.
result = skillpkg.add("leoyeai-nimble-web-search")
if result.exit_code:
    raise SystemExit(result.problems)

from agents import Agent, Runner
from decimalai.openai_agents import agent_config

# With no DECIMAL_API_KEY this reads the skills your project lists, from disk.
support = agent_config("support", fallback="You are a helpful agent.")

agent = Agent(
    name=support.name,
    instructions=support.instructions,  # your prompt, then the skill list
    tools=[*support.tools],             # your tools, then load_skill
)
# In a notebook or async code: result = await Runner.run(agent, "Hello!")
result = Runner.run_sync(agent, "Hello!")

Using SandboxAgent? capabilities=[Shell(), decimalai.openai_agents.sandbox_skills()] points its own loader at the same folder.

No DecimalAI package. The whole skill goes in every prompt, and nothing pins or updates it.

Copy SKILL.md

Save it in your project, as

.agents/skills/leoyeai-nimble-web-search/SKILL.md

Give it to your agent

from pathlib import Path
from agents import Agent, Runner

skill = Path(".agents/skills/leoyeai-nimble-web-search/SKILL.md").read_text()
agent = Agent(name="support", instructions=f"You are a helpful agent.\n\n{skill}")
# In a notebook or async code: result = await Runner.run(agent, "Hello!")
result = Runner.run_sync(agent, "Hello!")

This gets SKILL.md only. The skill's 5 other files are not included.

Other ways to add it

OpenAI Agents docs

agent_config() hands your agent the skill. With no DecimalAI key it reads your project's files and sends nothing. Needs SDK 0.27 or newer.

Install

pip install "decimalai[openai]"
decimalai skills add leoyeai-nimble-web-search

Add it to your agent

import json

from openai import OpenAI
from decimalai.openai import agent_config

client = OpenAI()
# With no DECIMAL_API_KEY this reads the skills your project lists, from disk.
support = agent_config("support", fallback="You are a helpful agent.")


def lookup_order(order_id: str) -> str:
    return f"Order {order_id} shipped yesterday."


# Your tools, as Chat Completions takes them, and what answers each.
TOOLS = [{"type": "function", "function": {
    "name": "lookup_order",
    "description": "Look up the status of an order.",
    "parameters": {"type": "object", "properties": {"order_id": {"type": "string"}},
                   "required": ["order_id"]},
}}]
FUNCTIONS = {"lookup_order": lookup_order}

question = "Where is order A1001?"
with support.run(question) as run:  # one user message, one run
    # run.system is your prompt, then the skill list.
    messages = [{"role": "system", "content": run.system}, run.message]
    while True:
        reply = client.chat.completions.create(
            model="gpt-5.4-mini",
            messages=messages,
            tools=[*TOOLS, *run.tools],  # your tools, then load_skill
        ).choices[0].message
        messages.append(reply)
        if not reply.tool_calls:
            break
        for call in reply.tool_calls:
            # load_skill is answered by the run; your own tools by FUNCTIONS.
            function = FUNCTIONS.get(call.function.name)
            messages.append(run.tool_result(call) or {
                "role": "tool", "tool_call_id": call.id,
                "content": function(**json.loads(call.function.arguments)) if function
                else f"There is no tool named {call.function.name!r}.",
            })
print(reply.content)

# The Responses API takes run.response_tools instead of run.tools.

Install

pip install "decimalai[openai]"

Add it to your agent

from decimalai import skillpkg

# Writes .agents/skills and .decimal/skills.toml. Safe to run twice.
result = skillpkg.add("leoyeai-nimble-web-search")
if result.exit_code:
    raise SystemExit(result.problems)

import json

from openai import OpenAI
from decimalai.openai import agent_config

client = OpenAI()
# With no DECIMAL_API_KEY this reads the skills your project lists, from disk.
support = agent_config("support", fallback="You are a helpful agent.")


def lookup_order(order_id: str) -> str:
    return f"Order {order_id} shipped yesterday."


# Your tools, as Chat Completions takes them, and what answers each.
TOOLS = [{"type": "function", "function": {
    "name": "lookup_order",
    "description": "Look up the status of an order.",
    "parameters": {"type": "object", "properties": {"order_id": {"type": "string"}},
                   "required": ["order_id"]},
}}]
FUNCTIONS = {"lookup_order": lookup_order}

question = "Where is order A1001?"
with support.run(question) as run:  # one user message, one run
    # run.system is your prompt, then the skill list.
    messages = [{"role": "system", "content": run.system}, run.message]
    while True:
        reply = client.chat.completions.create(
            model="gpt-5.4-mini",
            messages=messages,
            tools=[*TOOLS, *run.tools],  # your tools, then load_skill
        ).choices[0].message
        messages.append(reply)
        if not reply.tool_calls:
            break
        for call in reply.tool_calls:
            # load_skill is answered by the run; your own tools by FUNCTIONS.
            function = FUNCTIONS.get(call.function.name)
            messages.append(run.tool_result(call) or {
                "role": "tool", "tool_call_id": call.id,
                "content": function(**json.loads(call.function.arguments)) if function
                else f"There is no tool named {call.function.name!r}.",
            })
print(reply.content)

# The Responses API takes run.response_tools instead of run.tools.

No DecimalAI package. The whole skill goes in every prompt, and nothing pins or updates it.

Copy SKILL.md

Save it in your project, as

.agents/skills/leoyeai-nimble-web-search/SKILL.md

Give it to your agent

from pathlib import Path
from openai import OpenAI

client = OpenAI()
skill = Path(".agents/skills/leoyeai-nimble-web-search/SKILL.md").read_text()
reply = client.chat.completions.create(
    model="gpt-5.4-mini",
    messages=[
        {"role": "system", "content": f"You are a helpful agent.\n\n{skill}"},
        {"role": "user", "content": "Hello!"},
    ],
).choices[0].message

This gets SKILL.md only. The skill's 5 other files are not included.

Other ways to add it

OpenAI SDK docs

agent_config() hands your agent the skill. With no DecimalAI key it reads your project's files and sends nothing. Needs SDK 0.27 or newer.

Install

pip install "decimalai[anthropic]"
decimalai skills add leoyeai-nimble-web-search

Add it to your agent

import anthropic
from decimalai.anthropic import agent_config

client = anthropic.Anthropic()
# With no DECIMAL_API_KEY this reads the skills your project lists, from disk.
support = agent_config("support", fallback="You are a helpful agent.")

question = "Hello!"
with support.run(question) as run:  # one user message, one run
    answer = client.beta.messages.tool_runner(
        model="claude-haiku-5-5",
        max_tokens=4096,
        system=run.system,     # your prompt, then the skill list
        tools=[*run.tools],    # your tools, then load_skill
        messages=[{"role": "user", "content": question}],
    ).until_done()

Install

pip install "decimalai[anthropic]"

Add it to your agent

from decimalai import skillpkg

# Writes .agents/skills and .decimal/skills.toml. Safe to run twice.
result = skillpkg.add("leoyeai-nimble-web-search")
if result.exit_code:
    raise SystemExit(result.problems)

import anthropic
from decimalai.anthropic import agent_config

client = anthropic.Anthropic()
# With no DECIMAL_API_KEY this reads the skills your project lists, from disk.
support = agent_config("support", fallback="You are a helpful agent.")

question = "Hello!"
with support.run(question) as run:  # one user message, one run
    answer = client.beta.messages.tool_runner(
        model="claude-haiku-5-5",
        max_tokens=4096,
        system=run.system,     # your prompt, then the skill list
        tools=[*run.tools],    # your tools, then load_skill
        messages=[{"role": "user", "content": question}],
    ).until_done()

No DecimalAI package. The whole skill goes in every prompt, and nothing pins or updates it.

Copy SKILL.md

Save it in your project, as

.agents/skills/leoyeai-nimble-web-search/SKILL.md

Give it to your agent

from pathlib import Path
import anthropic

client = anthropic.Anthropic()
skill = Path(".agents/skills/leoyeai-nimble-web-search/SKILL.md").read_text()
reply = client.messages.create(
    model="claude-haiku-5-5",
    max_tokens=4096,
    system=f"You are a helpful agent.\n\n{skill}",
    messages=[{"role": "user", "content": "Hello!"}],
)

This gets SKILL.md only. The skill's 5 other files are not included.

Other ways to add it

Anthropic docs

agent_config() hands your agent the skill. With no DecimalAI key it reads your project's files and sends nothing. Needs SDK 0.27 or newer.

Install

pip install "decimalai[google-genai]"
decimalai skills add leoyeai-nimble-web-search

Add it to your agent

from google import genai
from google.genai import types
from decimalai.google_genai import agent_config

client = genai.Client()
# With no DECIMAL_API_KEY this reads the skills your project lists, from disk.
support = agent_config("support", fallback="You are a helpful agent.")


def lookup_order(order_id: str) -> str:
    return f"Order {order_id} shipped yesterday."


# Your functions, as declarations for the model, and what answers each.
TOOLS = [{"function_declarations": [{
    "name": "lookup_order",
    "description": "Look up the status of an order.",
    "parameters_json_schema": {"type": "object", "properties": {"order_id": {"type": "string"}},
                               "required": ["order_id"]},
}]}]
FUNCTIONS = {"lookup_order": lookup_order}

question = "Where is order A1001?"
with support.run(question) as run:  # one user message, one run
    config = types.GenerateContentConfig(
        system_instruction=run.system,     # your prompt, then the skill list
        tools=[*TOOLS, *run.tool_params],  # your functions, then load_skill
    )
    contents = [{"role": "user", "parts": [{"text": run.message}]}]
    while True:
        response = client.models.generate_content(
            model="gemini-3.5-flash", contents=contents, config=config,
        )
        if not response.function_calls:
            break
        contents.append(response.candidates[0].content)
        parts = []
        for call in response.function_calls:
            # load_skill is answered by the run; your own functions by FUNCTIONS.
            # A loop of your own rather than automatic function calling, which
            # raises KeyError when the model asks for a function you did not pass.
            function = FUNCTIONS.get(call.name)
            parts.append(run.tool_result(call) or {"function_response": {
                "name": call.name, "id": call.id,
                "response": {"result": function(**(call.args or {})) if function
                             else f"There is no function named {call.name!r}."},
            }})
        contents.append({"role": "user", "parts": parts})
print(response.text)

Install

pip install "decimalai[google-genai]"

Add it to your agent

from decimalai import skillpkg

# Writes .agents/skills and .decimal/skills.toml. Safe to run twice.
result = skillpkg.add("leoyeai-nimble-web-search")
if result.exit_code:
    raise SystemExit(result.problems)

from google import genai
from google.genai import types
from decimalai.google_genai import agent_config

client = genai.Client()
# With no DECIMAL_API_KEY this reads the skills your project lists, from disk.
support = agent_config("support", fallback="You are a helpful agent.")


def lookup_order(order_id: str) -> str:
    return f"Order {order_id} shipped yesterday."


# Your functions, as declarations for the model, and what answers each.
TOOLS = [{"function_declarations": [{
    "name": "lookup_order",
    "description": "Look up the status of an order.",
    "parameters_json_schema": {"type": "object", "properties": {"order_id": {"type": "string"}},
                               "required": ["order_id"]},
}]}]
FUNCTIONS = {"lookup_order": lookup_order}

question = "Where is order A1001?"
with support.run(question) as run:  # one user message, one run
    config = types.GenerateContentConfig(
        system_instruction=run.system,     # your prompt, then the skill list
        tools=[*TOOLS, *run.tool_params],  # your functions, then load_skill
    )
    contents = [{"role": "user", "parts": [{"text": run.message}]}]
    while True:
        response = client.models.generate_content(
            model="gemini-3.5-flash", contents=contents, config=config,
        )
        if not response.function_calls:
            break
        contents.append(response.candidates[0].content)
        parts = []
        for call in response.function_calls:
            # load_skill is answered by the run; your own functions by FUNCTIONS.
            # A loop of your own rather than automatic function calling, which
            # raises KeyError when the model asks for a function you did not pass.
            function = FUNCTIONS.get(call.name)
            parts.append(run.tool_result(call) or {"function_response": {
                "name": call.name, "id": call.id,
                "response": {"result": function(**(call.args or {})) if function
                             else f"There is no function named {call.name!r}."},
            }})
        contents.append({"role": "user", "parts": parts})
print(response.text)

No DecimalAI package. The whole skill goes in every prompt, and nothing pins or updates it.

Copy SKILL.md

Save it in your project, as

.agents/skills/leoyeai-nimble-web-search/SKILL.md

Give it to your agent

from pathlib import Path
from google import genai
from google.genai import types

client = genai.Client()
skill = Path(".agents/skills/leoyeai-nimble-web-search/SKILL.md").read_text()
response = client.models.generate_content(
    model="gemini-3.5-flash",
    contents="Hello!",
    config=types.GenerateContentConfig(system_instruction=f"You are a helpful agent.\n\n{skill}"),
)

This gets SKILL.md only. The skill's 5 other files are not included.

Other ways to add it

Gemini API docs

agent_config() hands your agent the skill. With no DecimalAI key it reads your project's files and sends nothing. Needs SDK 0.27 or newer.

Install

pip install "decimalai[langchain]" langchain-openai
decimalai skills add leoyeai-nimble-web-search

Add it to your agent

from langchain.agents import create_agent
from decimalai.langchain import agent_config

# With no DECIMAL_API_KEY this reads the skills your project lists, from disk.
support = agent_config("support", fallback="You are a helpful agent.")

agent = create_agent(
    "openai:gpt-5.4-mini",
    tools=[],                         # your tools; the middleware adds load_skill
    middleware=[support.middleware],  # your prompt, the skill list and load_skill
)
result = agent.invoke({"messages": [{"role": "user", "content": "Hello!"}]})

Install

pip install "decimalai[langchain]" langchain-openai

Add it to your agent

from decimalai import skillpkg

# Writes .agents/skills and .decimal/skills.toml. Safe to run twice.
result = skillpkg.add("leoyeai-nimble-web-search")
if result.exit_code:
    raise SystemExit(result.problems)

from langchain.agents import create_agent
from decimalai.langchain import agent_config

# With no DECIMAL_API_KEY this reads the skills your project lists, from disk.
support = agent_config("support", fallback="You are a helpful agent.")

agent = create_agent(
    "openai:gpt-5.4-mini",
    tools=[],                         # your tools; the middleware adds load_skill
    middleware=[support.middleware],  # your prompt, the skill list and load_skill
)
result = agent.invoke({"messages": [{"role": "user", "content": "Hello!"}]})

No DecimalAI package. The whole skill goes in every prompt, and nothing pins or updates it.

Copy SKILL.md

Save it in your project, as

.agents/skills/leoyeai-nimble-web-search/SKILL.md

Give it to your agent

from pathlib import Path
from langchain.agents import create_agent

skill = Path(".agents/skills/leoyeai-nimble-web-search/SKILL.md").read_text()
agent = create_agent("openai:gpt-5.4-mini", tools=[], system_prompt=f"You are a helpful agent.\n\n{skill}")
result = agent.invoke({"messages": [{"role": "user", "content": "Hello!"}]})

This gets SKILL.md only. The skill's 5 other files are not included.

Other ways to add it

LangChain docs

CrewAI's own skill loader reads the installed folder. No DecimalAI account needed.

Install

pip install "decimalai>=0.16" "crewai>=1.15.27"
decimalai skills add leoyeai-nimble-web-search

Add it to your agent

import decimalai.crewai
from crewai import Agent, Crew, Task

agent = Agent(
    role="Support", goal="Help the customer", backstory="A support agent.",
    llm=llm,                               # your own CrewAI LLM
    skills=decimalai.crewai.skills(),      # the installed folder
    tools=decimalai.crewai.skill_tools(),  # reads a skill's files, runs its scripts
)
task = Task(description="Hello!", expected_output="an answer", agent=agent)
Crew(agents=[agent], tasks=[task]).kickoff()

The same install from Python, for a notebook or a setup script. CrewAI's own skill loader reads the installed folder. No DecimalAI account needed.

Install

pip install "decimalai>=0.16" "crewai>=1.15.27"

Add it to your agent

from decimalai import skillpkg

# Writes .agents/skills and .decimal/skills.toml. Safe to run twice.
result = skillpkg.add("leoyeai-nimble-web-search")
if result.exit_code:
    raise SystemExit(result.problems)

import decimalai.crewai
from crewai import Agent, Crew, Task

agent = Agent(
    role="Support", goal="Help the customer", backstory="A support agent.",
    llm=llm,                               # your own CrewAI LLM
    skills=decimalai.crewai.skills(),      # the installed folder
    tools=decimalai.crewai.skill_tools(),  # reads a skill's files, runs its scripts
)
task = Task(description="Hello!", expected_output="an answer", agent=agent)
Crew(agents=[agent], tasks=[task]).kickoff()

No DecimalAI package. CrewAI's own loader reads the folder, and nothing pins or updates it.

Copy SKILL.md

Save it in your project, as

.agents/skills/leoyeai-nimble-web-search/SKILL.md

Give it to your agent

from pathlib import Path
from crewai import Agent, Crew, Task

agent = Agent(
    role="Support", goal="Help the customer", backstory="A support agent.",
    llm=llm,                         # your own CrewAI LLM
    skills=[Path(".agents/skills")],
)
task = Task(description="Hello!", expected_output="an answer", agent=agent)
Crew(agents=[agent], tasks=[task]).kickoff()

This gets SKILL.md only. The skill's 5 other files are not included.

Other ways to add it

CrewAI docs

agent_config() hands your agent the skill. With no DecimalAI key it reads your project's files and sends nothing. Needs SDK 0.27 or newer.

Install

pip install "decimalai[adk]"
decimalai skills add leoyeai-nimble-web-search

Add it to your agent

from decimalai.adk import DecimalAIPlugin, agent_config
from google.adk.agents import LlmAgent
from google.adk.apps import App

# With no DECIMAL_API_KEY this reads the skills your project lists, from disk.
support = agent_config("support", fallback="You are a helpful agent.")

agent = LlmAgent(
    name="support",          # ADK needs a Python identifier
    model="gemini-3.5-flash",
    instruction=support.instruction,  # your prompt, then the skill list
    tools=[*support.tools],           # your tools, then load_skill
)
# DecimalAIPlugin makes each invocation of runners built from this App one trace.
app = App(name="support", root_agent=agent, plugins=[DecimalAIPlugin()])

Prefer ADK's own loader? SkillToolset(skills=decimalai.adk.skills(), ...) reads the same folder. Use one or the other: a skill delivered both ways reaches the prompt twice.

Install

pip install "decimalai[adk]"

Add it to your agent

from decimalai import skillpkg

# Writes .agents/skills and .decimal/skills.toml. Safe to run twice.
result = skillpkg.add("leoyeai-nimble-web-search")
if result.exit_code:
    raise SystemExit(result.problems)

from decimalai.adk import DecimalAIPlugin, agent_config
from google.adk.agents import LlmAgent
from google.adk.apps import App

# With no DECIMAL_API_KEY this reads the skills your project lists, from disk.
support = agent_config("support", fallback="You are a helpful agent.")

agent = LlmAgent(
    name="support",          # ADK needs a Python identifier
    model="gemini-3.5-flash",
    instruction=support.instruction,  # your prompt, then the skill list
    tools=[*support.tools],           # your tools, then load_skill
)
# DecimalAIPlugin makes each invocation of runners built from this App one trace.
app = App(name="support", root_agent=agent, plugins=[DecimalAIPlugin()])

Prefer ADK's own loader? SkillToolset(skills=decimalai.adk.skills(), ...) reads the same folder. Use one or the other: a skill delivered both ways reaches the prompt twice.

No DecimalAI package. The whole skill goes in every prompt, and nothing pins or updates it.

Copy SKILL.md

Save it in your project, as

.agents/skills/leoyeai-nimble-web-search/SKILL.md

Give it to your agent

from pathlib import Path
from google.adk.agents import LlmAgent

skill = Path(".agents/skills/leoyeai-nimble-web-search/SKILL.md").read_text()
agent = LlmAgent(
    name="support",
    model="gemini-3.5-flash",
    instruction=lambda context: f"You are a helpful agent.\n\n{skill}",
)

This gets SKILL.md only. The skill's 5 other files are not included.

Other ways to add it

Google ADK docs

agent_config() hands your agent the skill. With no DecimalAI key it reads your project's files and sends nothing. Needs SDK 0.27 or newer.

Install

pip install "decimalai[pydantic-ai]"
decimalai skills add leoyeai-nimble-web-search

Add it to your agent

from pydantic_ai import Agent
from decimalai.pydantic_ai import agent_config

# With no DECIMAL_API_KEY this reads the skills your project lists, from disk.
support = agent_config("support", fallback="You are a helpful agent.")

agent = Agent(
    "openai:gpt-4o-mini",
    name=support.name,
    tools=[],                 # your tools; the capability adds load_skill
    capabilities=[support],   # your prompt, the skill list and load_skill
)
# In a notebook or async code: result = await agent.run("Hello!")
result = agent.run_sync("Hello!")

On the Pydantic AI harness, decimalai.pydantic_ai_harness.skills(project) uses its own loader instead.

Install

pip install "decimalai[pydantic-ai]"

Add it to your agent

from decimalai import skillpkg

# Writes .agents/skills and .decimal/skills.toml. Safe to run twice.
result = skillpkg.add("leoyeai-nimble-web-search")
if result.exit_code:
    raise SystemExit(result.problems)

from pydantic_ai import Agent
from decimalai.pydantic_ai import agent_config

# With no DECIMAL_API_KEY this reads the skills your project lists, from disk.
support = agent_config("support", fallback="You are a helpful agent.")

agent = Agent(
    "openai:gpt-4o-mini",
    name=support.name,
    tools=[],                 # your tools; the capability adds load_skill
    capabilities=[support],   # your prompt, the skill list and load_skill
)
# In a notebook or async code: result = await agent.run("Hello!")
result = agent.run_sync("Hello!")

On the Pydantic AI harness, decimalai.pydantic_ai_harness.skills(project) uses its own loader instead.

No DecimalAI package. The whole skill goes in every prompt, and nothing pins or updates it.

Copy SKILL.md

Save it in your project, as

.agents/skills/leoyeai-nimble-web-search/SKILL.md

Give it to your agent

from pathlib import Path
from pydantic_ai import Agent

skill = Path(".agents/skills/leoyeai-nimble-web-search/SKILL.md").read_text()
agent = Agent("openai:gpt-4o-mini", instructions=f"You are a helpful agent.\n\n{skill}")
# In a notebook or async code: result = await agent.run("Hello!")
result = agent.run_sync("Hello!")

This gets SKILL.md only. The skill's 5 other files are not included.

Other ways to add it

Pydantic AI docs

Deep Agents' own skill loader reads the installed folder. No DecimalAI account needed.

Install

pip install "decimalai>=0.16" deepagents
decimalai skills add leoyeai-nimble-web-search

Add it to your agent

import decimalai.deepagents
from deepagents import create_deep_agent

agent = create_deep_agent(model=model, **decimalai.deepagents.skills())
agent.invoke({"messages": [{"role": "user", "content": "Hello!"}]})

The default backend reads files but has no shell. To run a skill's scripts, pass skills(backend=LocalShellBackend(...)).

The same install from Python, for a notebook or a setup script. Deep Agents' own skill loader reads the installed folder. No DecimalAI account needed.

Install

pip install "decimalai>=0.16" deepagents

Add it to your agent

from decimalai import skillpkg

# Writes .agents/skills and .decimal/skills.toml. Safe to run twice.
result = skillpkg.add("leoyeai-nimble-web-search")
if result.exit_code:
    raise SystemExit(result.problems)

import decimalai.deepagents
from deepagents import create_deep_agent

agent = create_deep_agent(model=model, **decimalai.deepagents.skills())
agent.invoke({"messages": [{"role": "user", "content": "Hello!"}]})

The default backend reads files but has no shell. To run a skill's scripts, pass skills(backend=LocalShellBackend(...)).

No DecimalAI package. The whole skill goes in every prompt, and nothing pins or updates it.

Copy SKILL.md

Save it in your project, as

.agents/skills/leoyeai-nimble-web-search/SKILL.md

Give it to your agent

from pathlib import Path
from deepagents import create_deep_agent

skill = Path(".agents/skills/leoyeai-nimble-web-search/SKILL.md").read_text()
agent = create_deep_agent(model=model, system_prompt=f"You are a helpful agent.\n\n{skill}")
agent.invoke({"messages": [{"role": "user", "content": "Hello!"}]})

This gets SKILL.md only. The skill's 5 other files are not included.

Other ways to add it

Deep Agents docs

Its own skill loader reads the installed folder. No DecimalAI account needed.

Install

pip install "decimalai>=0.16" agent-framework
decimalai skills add leoyeai-nimble-web-search

Add it to your agent

import asyncio

from agent_framework import Agent
from decimalai.agent_framework import skills

agent = Agent(client=client, instructions="You are a helpful agent.", context_providers=[skills()])
asyncio.run(agent.run("Hello!"))

It caches skills by default, so restart the process after decimalai skills update.

The same install from Python, for a notebook or a setup script. Its own skill loader reads the installed folder. No DecimalAI account needed.

Install

pip install "decimalai>=0.16" agent-framework

Add it to your agent

from decimalai import skillpkg

# Writes .agents/skills and .decimal/skills.toml. Safe to run twice.
result = skillpkg.add("leoyeai-nimble-web-search")
if result.exit_code:
    raise SystemExit(result.problems)

import asyncio

from agent_framework import Agent
from decimalai.agent_framework import skills

agent = Agent(client=client, instructions="You are a helpful agent.", context_providers=[skills()])
asyncio.run(agent.run("Hello!"))

It caches skills by default, so restart the process after decimalai skills update.

No DecimalAI package. The whole skill goes in every prompt, and nothing pins or updates it.

Copy SKILL.md

Save it in your project, as

.agents/skills/leoyeai-nimble-web-search/SKILL.md

Give it to your agent

import asyncio
from pathlib import Path
from agent_framework import Agent

skill = Path(".agents/skills/leoyeai-nimble-web-search/SKILL.md").read_text()
agent = Agent(client=client, instructions=f"You are a helpful agent.\n\n{skill}")
asyncio.run(agent.run("Hello!"))

This gets SKILL.md only. The skill's 5 other files are not included.

Other ways to add it

Microsoft Agent Framework docs

Strands' own skill loader reads the installed folder. No DecimalAI account needed.

Install

pip install "decimalai>=0.16" strands-agents
decimalai skills add leoyeai-nimble-web-search

Add it to your agent

from decimalai.strands import skills
from strands import Agent
from strands.vended_tools import file_editor, shell

agent = Agent(
    model=model,                # always pass one: the default is Amazon Bedrock
    system_prompt="You are a helpful agent.",
    tools=[file_editor, shell],
    plugins=[skills()],
)
agent("Hello!")

Strands loads an agent's skills once, so build the agent again after decimalai skills update.

The same install from Python, for a notebook or a setup script. Strands' own skill loader reads the installed folder. No DecimalAI account needed.

Install

pip install "decimalai>=0.16" strands-agents

Add it to your agent

from decimalai import skillpkg

# Writes .agents/skills and .decimal/skills.toml. Safe to run twice.
result = skillpkg.add("leoyeai-nimble-web-search")
if result.exit_code:
    raise SystemExit(result.problems)

from decimalai.strands import skills
from strands import Agent
from strands.vended_tools import file_editor, shell

agent = Agent(
    model=model,                # always pass one: the default is Amazon Bedrock
    system_prompt="You are a helpful agent.",
    tools=[file_editor, shell],
    plugins=[skills()],
)
agent("Hello!")

Strands loads an agent's skills once, so build the agent again after decimalai skills update.

No DecimalAI package. The whole skill goes in every prompt, and nothing pins or updates it.

Copy SKILL.md

Save it in your project, as

.agents/skills/leoyeai-nimble-web-search/SKILL.md

Give it to your agent

from pathlib import Path
from strands import Agent

skill = Path(".agents/skills/leoyeai-nimble-web-search/SKILL.md").read_text()
agent = Agent(model=model, system_prompt=f"You are a helpful agent.\n\n{skill}")
agent("Hello!")

This gets SKILL.md only. The skill's 5 other files are not included.

Other ways to add it

Strands docs

Adds every file the skill has, pinned so you can update it. Cursor, Copilot, Cline and Warp read this folder by themselves.

pip install "decimalai>=0.15"
decimalai skills add leoyeai-nimble-web-search

No Python or account. Cursor, Copilot, Cline and Warp read this folder by themselves.

Save it into your project

curl -fsSL --create-dirs -o .agents/skills/leoyeai-nimble-web-search/SKILL.md https://app.decimal.ai/s/leoyeai-nimble-web-search/SKILL.md

Copy SKILL.md

Save it in your project, as

.agents/skills/leoyeai-nimble-web-search/SKILL.md

This gets SKILL.md only. The skill's 5 other files are not included.

Other ways to add it

Cursor and other editors docs

Fetch the file and give its text to your model as instructions. No account or package needed.

Get the file

curl -fsSL https://app.decimal.ai/s/leoyeai-nimble-web-search/SKILL.md

Read the summary as JSON

curl -fsSL https://app.decimal.ai/s/leoyeai-nimble-web-search.json

This gets SKILL.md only. The skill's 5 other files are not included.

Other ways to add it

Other setups docs

You don't need a DecimalAI account.

Version: v1, tested 8/8/2026
Source: LeoYeAI/openclaw-master-skills ↗
License: MIT

Manage it in DecimalAI

Saved prompts and skills, pinned versions, and traces of this skill in your runs. DecimalAI does not run your agent.

Claude Code reads files from your project, so DecimalAI config does not apply there.

On Claude Agent SDK: save the skill to an agent here, set DECIMAL_API_KEY, and the same code uses it with no command to run. Changes you save reach the next run with no redeploy.

On OpenAI Agents: save the skill to an agent here, set DECIMAL_API_KEY, and the same code uses it with no command to run. Changes you save reach the next run with no redeploy.

On OpenAI SDK: save the skill to an agent here, set DECIMAL_API_KEY, and the same code uses it with no command to run. Changes you save reach the next run with no redeploy.

On Anthropic: save the skill to an agent here, set DECIMAL_API_KEY, and the same code uses it with no command to run. Changes you save reach the next run with no redeploy.

On Gemini API: save the skill to an agent here, set DECIMAL_API_KEY, and the same code uses it with no command to run. Changes you save reach the next run with no redeploy.

On LangChain: save the skill to an agent here, set DECIMAL_API_KEY, and the same code uses it with no command to run. Changes you save reach the next run with no redeploy.

On CrewAI: set DECIMAL_API_KEY and add decimalai.init(crewai=True) to record runs and skill use. The skill version stays in your repo.

On Google ADK: save the skill to an agent here, set DECIMAL_API_KEY, and the same code uses it with no command to run. Changes you save reach the next run with no redeploy.

On Pydantic AI: save the skill to an agent here, set DECIMAL_API_KEY, and the same code uses it with no command to run. Changes you save reach the next run with no redeploy.

On Deep Agents: set DECIMAL_API_KEY and add decimalai.init(langchain=True) to record runs and skill use. The skill version stays in your repo.

On Microsoft Agent Framework: set DECIMAL_API_KEY and add decimalai.init(otel=True, agent_name="support") to record runs and skill use. The skill version stays in your repo.

On Strands: set DECIMAL_API_KEY and add decimalai.init(otel=True, agent_name="support") to record runs and skill use. The skill version stays in your repo.

Editors read files from your project, so DecimalAI config does not apply there.

Anywhere else: record a use with decimalai.log_skill_activation() inside a trace.

Use this skill

SKILL.md

Nimble Web Search

Real-time web intelligence using Nimble Search API with specialized focus modes and AI-powered result synthesis.

Prerequisites

Nimble API Key Required - Get your key at https://www.nimbleway.com/

Configuration

Set the NIMBLE_API_KEY environment variable using your platform's method:

Claude Code:

// ~/.claude/settings.json
{
  "env": {
    "NIMBLE_API_KEY": "your-api-key-here"
  }
}

VS Code/GitHub Copilot:

Add to .github/skills/ directory in your repository
Or use GitHub Actions secrets for the copilot environment

Shell/Terminal:

export NIMBLE_API_KEY="your-api-key-here"

Any Platform: The skill checks for the NIMBLE_API_KEY environment variable regardless of how you set it.

API Key Validation

IMPORTANT: Before making any search request, verify the API key is configured:

# Check if API key is set
if [ -z "$NIMBLE_API_KEY" ]; then
  echo "❌ Error: NIMBLE_API_KEY not configured"
  echo ""
  echo "Get your API key: https://www.nimbleway.com/"
  echo ""
  echo "Configure using your platform's method:"
  echo "- Claude Code: Add to ~/.claude/settings.json"
  echo "- GitHub Copilot: Use GitHub Actions secrets"
  echo "- Shell: export NIMBLE_API_KEY=\"your-key\""
  echo ""
  echo "Do NOT fall back to other search tools - guide the user to configure first."
  exit 1
fi

Overview

Nimble Search provides real-time web intelligence with 8 specialized focus modes optimized for different types of queries. Get instant access to current web data with AI-powered answer generation, deep content extraction, URL discovery, and smart filtering by domain and date.

IMPORTANT: Always Specify These Parameters

When using this skill, always explicitly set the following parameters in your requests:

deep_search: Default to false for 5-10x faster responses
- Use false (FAST MODE - 1-3 seconds): For 95% of use cases - URL discovery, research, comparisons, answer generation
- Use true (DEEP MODE - 5-15 seconds): Only when you specifically need full page content extracted for archiving or detailed analysis
focus: Default to "general" for broad searches
- Change to specific mode (coding, news, academic, shopping, social, geo, location) for targeted results
max_results: Default to 10 - Balanced speed and coverage

Performance Awareness: By explicitly setting deep_search: false, you're choosing fast mode and should expect results in 1-3 seconds. If you set deep_search: true, expect 5-15 seconds response time.

Quick Start

Use the wrapper script for the simplest experience:

# ALWAYS specify deep_search explicitly
./scripts/search.sh '{
  "query": "React hooks",
  "deep_search": false
}'

The script automatically handles authentication, tracking headers, and output formatting.

When to Use Each Mode

Use deep_search: false (FAST MODE - 1-3 seconds) - Default for 95% of cases:

✅ Finding URLs and discovering resources
✅ Research and topic exploration
✅ Answer generation and summaries
✅ Product comparisons
✅ News monitoring
✅ Any time you DON'T need full article text

Use deep_search: true (DEEP MODE - 5-15 seconds) - Only when specifically needed:

📄 Archiving full article content
📄 Extracting complete documentation
📄 Building text datasets
📄 Processing full page content for analysis

Decision Rule: If you're not sure, use deep_search: false. You can always re-run with true if needed.

Core Capabilities

Focus Modes

Choose the appropriate focus mode based on your query type:

general - Default mode for broad web searches
coding - Real-time access to technical documentation, code examples, programming resources
news - Real-time news articles, current events, breaking stories
academic - Research papers, scholarly articles, academic resources
shopping - Real-time product searches, e-commerce results, price comparisons
social - Real-time social media posts, discussions, trending community content
geo - Location-based searches, geographic information
location - Local business searches, place-specific queries

Search Features

LLM Answer Generation

Request AI-generated answers synthesized from search results
Powered by Claude for high-quality summaries
Include citations to source URLs
Best for: Research questions, topic overviews, comparative analysis

URL Discovery

Extract 1-20 most relevant URLs for a query
Useful for building reading lists and reference collections
Returns URLs with titles and descriptions
Best for: Resource gathering, link building, research preparation

Deep Content Extraction

Default (Recommended): deep_search=false - Fastest response, returns titles, descriptions, and URLs
Optional: deep_search=true - Slower, extracts full page content
Important: Most use cases work perfectly with deep_search=false (the default)
Available formats when deep_search=true: markdown, plain_text, simplified_html
Only enable deep search for: Detailed content analysis, archiving, or comprehensive text extraction needs

Domain Filtering

Include specific domains (e.g., github.com, stackoverflow.com)
Exclude domains to remove unwanted sources
Combine multiple domains for focused searches
Best for: Targeted research, brand monitoring, competitive analysis

Time Filtering

Recommended: Use time_range for real-time recency filtering (hour, day, week, month, year)
Alternative: Use start_date/end_date for precise date ranges (YYYY-MM-DD)
Note: time_range and date filters are mutually exclusive
Best for: Real-time news monitoring, recent developments, temporal analysis

Usage Patterns

All examples below use the ./scripts/search.sh wrapper for simplicity. For raw API usage, see the API Integration section.

Basic Search

Quick search in fast mode (ALWAYS specify deep_search explicitly):

./scripts/search.sh '{
  "query": "React Server Components tutorial",
  "deep_search": false
}'

For technical content, specify coding focus (still fast mode):

./scripts/search.sh '{
  "query": "React Server Components tutorial",
  "focus": "coding",
  "deep_search": false
}'

Research with AI Summary

Get synthesized insights from multiple sources (fast mode works great with answer generation):

./scripts/search.sh '{
  "query": "impact of AI on software development 2026",
  "deep_search": false,
  "include_answer": true
}'

Domain-Specific Search

Target specific authoritative sources (fast mode):

./scripts/search.sh '{
  "query": "async await patterns",
  "focus": "coding",
  "deep_search": false,
  "include_domains": ["github.com", "stackoverflow.com", "dev.to"],
  "max_results": 8
}'

Real-Time News Monitoring

Track current events and breaking news as they happen (fast mode):

./scripts/search.sh '{
  "query": "latest developments in quantum computing",
  "focus": "news",
  "deep_search": false,
  "time_range": "week",
  "max_results": 15,
  "include_answer": true
}'

Academic Research - Fast Mode (Recommended)

Find and synthesize scholarly content using fast mode:

./scripts/search.sh '{
  "query": "machine learning interpretability methods",
  "focus": "academic",
  "deep_search": false,
  "max_results": 20,
  "include_answer": true
}'

When to use deep mode: Only use "deep_search": true if you need full paper content extracted for archiving:

./scripts/search.sh '{
  "query": "machine learning interpretability methods",
  "focus": "academic",
  "deep_search": true,
  "max_results": 5,
  "output_format": "markdown"
}'

Note: Deep mode is 5-15x slower. Use only when specifically needed.

Real-Time Shopping Research

Compare products and current prices (fast mode):

./scripts/search.sh '{
  "query": "best mechanical keyboards for programming",
  "focus": "shopping",
  "deep_search": false,
  "max_results": 10,
  "include_answer": true
}'

Parallel Search Strategies

When to Use Parallel Searches

Run multiple real-time searches in parallel when:

Comparing perspectives: Search the same topic across different focus modes
Multi-faceted research: Investigate different aspects of a topic simultaneously
Competitive analysis: Search multiple domains or competitors at once
Real-time monitoring: Track multiple topics or keywords concurrently
Cross-validation: Verify information across different source types in real-time

Implementation Methods

Method 1: Background Processes (Recommended)

Run multiple searches concurrently using the wrapper script:

# Start multiple searches in parallel
./scripts/search.sh '{"query": "React", "focus": "coding"}' > react_coding.json &
./scripts/search.sh '{"query": "React", "focus": "news"}' > react_news.json &
./scripts/search.sh '{"query": "React", "focus": "academic"}' > react_academic.json &

# Wait for all to complete
wait

# Combine results
jq -s '.' react_*.json > combined_results.json

Method 2: Loop with xargs (Controlled Parallelism)

Process multiple queries with rate limiting:

# Create queries file
cat > queries.txt <<EOF
{"query": "AI frameworks", "focus": "coding"}
{"query": "AI regulation", "focus": "news"}
{"query": "AI research", "focus": "academic"}
EOF

# Run with max 3 parallel processes
cat queries.txt | xargs -n1 -P3 -I{} ./scripts/search.sh '{}'

Method 3: Focus Mode Comparison

Search the same query across different focus modes:

QUERY="artificial intelligence trends"

for focus in "general" "coding" "news" "academic"; do
  (
    ./scripts/search.sh "{\"query\": \"$QUERY\", \"focus\": \"$focus\"}" \
      > "${focus}_results.json"
  ) &
done

wait
echo "All searches complete!"

Best Practices for Parallel Execution

Rate Limiting: Limit parallel requests to 3-5 to avoid overwhelming the API
- Use xargs -P3 to set maximum concurrent requests
- Check your API tier limits before increasing parallelism

Error Handling: Capture and handle failures gracefully

./scripts/search.sh '{"query": "test"}' || echo "Search failed" >> errors.log

Result Aggregation: Combine results after all searches complete

# Wait for all searches
wait

# Merge JSON results
jq -s 'map(.results) | flatten' result*.json > combined.json

Progress Tracking: Monitor completion status

echo "Running 5 parallel searches..."

for i in {1..5}; do
  ./scripts/search.sh "{\"query\": \"query$i\"}" > "result$i.json" &
done

wait
echo "All searches complete!"

Example: Multi-Perspective Research

#!/bin/bash
# Research a topic across multiple focus modes simultaneously

QUERY="artificial intelligence code generation"
OUTPUT_DIR="./search_results"
mkdir -p "$OUTPUT_DIR"

# Run searches in parallel across different focus modes
for focus in "general" "coding" "news" "academic"; do
  (
    ./scripts/search.sh "{
      \"query\": \"$QUERY\",
      \"focus\": \"$focus\",
      \"max_results\": 10
    }" > "$OUTPUT_DIR/${focus}_results.json"
  ) &
done

# Wait for all searches to complete
wait

# Aggregate and analyze results
jq -s '{
  general: .[0].results,
  coding: .[1].results,
  news: .[2].results,
  academic: .[3].results
}' "$OUTPUT_DIR"/*.json > "$OUTPUT_DIR/combined_analysis.json"

echo "✓ Multi-perspective search complete"

Performance Considerations

Optimal Parallelism: 3-5 concurrent requests balances speed and API limits
Memory Usage: Each parallel request consumes memory; monitor for large result sets
Network Bandwidth: Parallel requests can saturate bandwidth on slow connections
API Costs: More parallel requests = faster API quota consumption

When NOT to Use Parallel Searches

Single, focused query with one clear answer
Sequential research where each search informs the next
API quota is limited or expensive
Results need to be processed before next search
Simple URL collection that doesn't require multiple perspectives

API Integration

Note: For most use cases, use the ./scripts/search.sh wrapper script shown in Usage Patterns. The raw API examples below are for advanced users who need direct API access or custom integration.

Required Configuration

Before making any API request, always validate the API key is configured:

# Validate API key is set
if [ -z "$NIMBLE_API_KEY" ]; then
  echo "❌ Nimble API key not configured."
  echo "Get your key at https://www.nimbleway.com/"
  echo ""
  echo "Set NIMBLE_API_KEY environment variable using your platform's method."
  exit 1
fi

The skill requires the NIMBLE_API_KEY environment variable. See Prerequisites for platform-specific setup instructions.

Get your API key at: https://www.nimbleway.com/

API Endpoint

POST https://nimble-retriever.webit.live/search

Request Format

{
  "query": "search query string",  // REQUIRED
  "focus": "general",  // OPTIONAL: default "general" | coding|news|academic|shopping|social|geo|location
  "max_results": 10,  // OPTIONAL: default 10 (range: 1-100)
  "include_answer": false,  // OPTIONAL: default false
  "deep_search": false,  // OPTIONAL: default false (RECOMMENDED: keep false for speed)
  "output_format": "markdown",  // OPTIONAL: default "markdown" | plain_text|simplified_html
  "include_domains": ["domain1.com"],  // OPTIONAL: default [] (no filter)
  "exclude_domains": ["domain3.com"],  // OPTIONAL: default [] (no filter)
  "time_range": "week",  // OPTIONAL: hour|day|week|month|year
  "start_date": "2026-01-01",  // OPTIONAL: Use time_range OR start_date/end_date (not both)
  "end_date": "2026-12-31"  // OPTIONAL
}

Key Defaults:

focus: "general" - Change to specific mode for targeted results
deep_search: false - Keep false unless you need full page content
max_results: 10 - Balanced speed and coverage

Response Format

{
  "results": [
    {
      "url": "https://example.com/page",
      "title": "Page Title",
      "description": "Page description",
      "content": "Full page content (if deep_search=true)",
      "published_date": "2026-01-15"
    }
  ],
  "include_answer": "AI-generated summary (if include_answer=true)",
  "urls": ["url1", "url2", "url3"],
  "total_results": 10
}

Best Practices

Focus Mode Selection

Use coding for:

Programming questions
Technical documentation
Code examples and tutorials
API references
Framework guides

Use news for:

Real-time current events
Breaking stories as they happen
Recent announcements
Trending topics
Time-sensitive information

Use academic for:

Research papers
Scholarly articles
Scientific studies
Academic journals
Citations and references

Use shopping for:

Product searches
Price comparisons
E-commerce research
Product reviews
Buying guides

Use social for:

Real-time social media monitoring
Live community discussions
Current user-generated content
Trending hashtags and topics
Real-time public sentiment

Use geo for:

Geographic information
Regional data
Maps and locations
Area-specific queries

Use location for:

Local business searches
Place-specific information
Nearby services
Regional recommendations

Result Limits

Quick searches: 5-10 results for fast overview
Comprehensive research: 15-20 results for depth
Answer generation: 10-15 results for balanced synthesis
URL collection: 20 results for comprehensive resource list

When to Use LLM Answers

✅ Use LLM answers when:

You need a synthesized overview of a topic
Comparing multiple sources or approaches
Summarizing recent developments
Answering specific questions
Creating research summaries

❌ Skip LLM answers when:

You just need a list of URLs
Building a reference collection
Speed is critical
You want to analyze sources manually
Original source text is needed

Content Extraction

Default (Recommended): deep_search=false

The default setting works for 95% of use cases:

✅ Fastest response times
✅ Returns titles, descriptions, URLs
✅ Works perfectly with include_answer=true
✅ Sufficient for research, comparisons, and URL discovery

Only use deep_search=true when you specifically need:

Full page content extraction
Archiving complete articles
Processing full text for analysis
Building comprehensive datasets

Performance impact:

deep_search=false: ~1-3 seconds
deep_search=true: ~5-15 seconds (significantly slower)

Error Handling

Common Issues

Authentication Failed

Verify NIMBLE_API_KEY is set correctly
Check API key is active at nimbleway.com
Ensure key has search API access

Rate Limiting

Reduce max_results
Add delays between requests
Check your plan limits
Consider upgrading API tier

No Results

Try different focus mode
Broaden search query
Remove domain filters
Adjust date filters

Timeout Errors

Reduce max_results
Disable deep content extraction
Simplify query
Try again after brief delay

Performance Tips

Use Defaults: Keep deep_search=false (default) for 5-10x faster responses
Start Simple: Begin with just {"query": "..."} - defaults work great
Choose Right Focus: Proper focus mode dramatically improves relevance (default: "general")
Optimize Result Count: Default of 10 results balances speed and coverage
Domain Filtering: Pre-filter sources for faster, more relevant results
Avoid Deep Search: Only enable deep_search=true when you truly need full content
Batch Queries: Group related searches to minimize API calls
Cache Results: Store results locally when appropriate

Integration Examples

See the examples/ directory for detailed integration patterns:

basic-search.md - Simple search implementation
deep-research.md - Multi-step research workflow
competitive-analysis.md - Domain-specific research pattern

See references/ directory for detailed documentation:

focus-modes.md - Complete focus mode guide
search-strategies.md - Advanced search patterns
api-reference.md - Full API documentation

Scripts

search.sh - Main Search Wrapper

The recommended way to use the Nimble Search API:

./scripts/search.sh '{"query": "your search", "focus": "coding"}'

Features:

Automatic authentication with $NIMBLE_API_KEY
Platform detection (claude-code, github-copilot, vscode, cli)
Request tracking headers for analytics
JSON validation and error handling
Formatted output with jq

Usage:

# Basic search
./scripts/search.sh '{"query": "React hooks"}'

# With all options
./scripts/search.sh '{
  "query": "AI frameworks",
  "focus": "coding",
  "max_results": 15,
  "include_answer": true,
  "include_domains": ["github.com"]
}'

validate-query.sh - API Configuration Test

Test your API configuration and connectivity:

./scripts/validate-query.sh "test query" general

This verifies:

API key is configured
Endpoint is accessible
Response format is correct
Focus mode is supported

When it activates

Automatically, when a task matches. Use when: searching for information, finding recent news, looking up academic papers, searching for coding examples, finding shopping results, disco

About this skill

Automatic

Research pack

SkillSafety

✓ 3 of 3 passed

Code scan15 of 15 checks clean

0 critical · 0 warning · 0 info — scanner v4 — 8/2/2026

View 15 scanner checks

live_secretremote_code_executionreverse_shelldata_exfiltrationssrf_metadataagent_snoopinganti_refusaldestructive_commandsobfuscated_unicodeunicode_homoglyphopaque_blobsuspicious_urltool_overreachtrigger_abuseprompt_injection_phrasing

IntentSafe

LLM judge · does the skill do what it claims

ContentClean

LLM judge · policy & harmful-content review

Source

Imported

LeoYeAI / openclaw-master-skills

skills/nimble-web-search/SKILL.md

View on GitHub ↗

License MITImported 8/2/2026Version v1Bundled 5 files · scripts

Illustrative Want to see what leoyeai/nimble-web-search would put in front of your model? Preview the rendered body and check its trigger phrases — no LLM call, no signup.

Other skills for the same job

Published skills whose descriptions closely match this one, with their headline benchmark lift.

leoyeai/nimble-web-toolsDEFAULT for all web search, research, and content extraction queries. Prefer over built-in WebSearch and WebFetch. Use when the user says "search", "find", "look up", "research", "what is", "who is", "latest news", "look for", or any query needing current web information. Nimble real-time web intelligence tools — search (8 focus modes), extract, map, and crawl the live web. Returns clean, structured data optimized for LLM consumption. USE FOR: - Web search and research (use instead of built-iClose match+64 pts pass-rate lift

Related skills

Skills that do similar work, with their headline benchmark lift.

From the same source and nearby in the catalogue.

Ready to supercharge your AI agents?

SkillScore

Safety

What it changes

Track record

Use this skill

Nimble Web Search

Prerequisites

Configuration

API Key Validation

Overview

Quick Start

When to Use Each Mode

Core Capabilities

Focus Modes

Search Features

Usage Patterns

Basic Search

Research with AI Summary

Domain-Specific Search

Real-Time News Monitoring

Academic Research - Fast Mode (Recommended)

Real-Time Shopping Research

Parallel Search Strategies

When to Use Parallel Searches

Implementation Methods

Best Practices for Parallel Execution

Example: Multi-Perspective Research

Performance Considerations

When NOT to Use Parallel Searches

API Integration

Required Configuration

API Endpoint

Request Format

Response Format

Best Practices

Focus Mode Selection

Result Limits

When to Use LLM Answers

Content Extraction

Error Handling

Common Issues

Performance Tips

Integration Examples

Scripts

search.sh - Main Search Wrapper

validate-query.sh - API Configuration Test

When it activates

SkillSafety

Source

Other skills for the same job

Related skills

More in the registry